Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 101
    Prev
    Next
    INDEX
    Explanations

    discussions about scientific theories and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names of people and dialogue markers in text.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.77
    RegistryLite
    -0.75
    +#+#
    -0.75
    protoimpl
    -0.73
     Waray
    -0.72
     transférez
    -0.72
     otomatig
    -0.71
     AssemblyCulture
    -0.71
     kasarigan
    -0.68
     ligiloj
    -0.68
    POSITIVE LOGITS
     statement
    0.42
    気
    0.33
    statement
    0.30
    عاية
    0.30
    a
    0.29
    нти
    0.29
     imp
    0.28
     sounding
    0.28
     прав
    0.28
     Stahl
    0.28
    Activations Density 0.327%

    No Known Activations